HDDS-14816. Add Recon AI Assistant backend foundation with Multi LLM integration by ArafatKhan2198 · Pull Request #9915 · apache/ozone

ArafatKhan2198 · 2026-03-13T08:27:23Z

What changes were proposed in this pull request?

What the Recon AI Chatbot Does (For Context)

The Recon AI Assistant is an intelligent query interface that bridges the gap between natural language and Recon's complex REST APIs. Instead of requiring administrators to memorize API endpoints and manually parse JSON payloads, the chatbot acts as an autonomous agent.

Example Scenario:
User Question: > "How many datanodes are unhealthy?"

The Traditional Workflow:

Administrator identifies the correct API endpoint (/containers/unhealthy or /datanodes).
Administrator executes a curl command.
Administrator manually parses the returned JSON payload.
Administrator aggregates the data to find the answer.

The New Chatbot Workflow:

The user asks the question in plain English via the Recon UI or Chatbot API.
The Chatbot Agent leverages the LLMDispatcher to consult the AI model.
The AI autonomously selects the correct internal Recon API based on the system guide and executes it.
The backend synthesizes the resulting JSON and returns a concise, human-readable summary back to the user.

Recon AI Chatbot: Backend Architecture Guide - https://docs.google.com/document/d/1jyYZz0llKwN7lexJzVRjxfzl1Iwdbx8dABwLXGzAajQ/edit?tab=t.0

What is the link to the Apache JIRA

https://issues.apache.org/jira/browse/HDDS-14816

How was this patch tested?

Here is what you can add to the "How was this patch tested?" section of your PR description. I have formatted it to clearly show the testing methodology, the script you used to verify the multi-model routing, and the configuration instructions needed for reviewers to reproduce it!

How was this patch tested?

This patch was tested by configuring all three supported AI providers (Google Gemini, OpenAI, and Anthropic) via Docker configuration, and programmatically looping through 9 different AI models to verify that the LLMDispatcher correctly routes natural language queries to the appropriate provider without requiring the user to specify it.

1. Configuration Setup

To test this locally, reviewers can configure their API keys by adding the following properties to their docker-config file:

# Set the desired default provider (optional, defaults to gemini)
OZONE-SITE.XML_ozone.recon.chatbot.provider=gemini

# Provider API Keys
OZONE-SITE.XML_ozone.recon.chatbot.gemini.api.key=YOUR_GEMINI_API_KEY
OZONE-SITE.XML_ozone.recon.chatbot.openai.api.key=YOUR_OPENAI_API_KEY
OZONE-SITE.XML_ozone.recon.chatbot.anthropic.api.key=YOUR_CLAUDE_API_KEY

2. API Verification Script

A shell script was used to hit the Chatbot REST API (/api/v1/chatbot/chat), iterating through a predefined list of models to ensure proxying worked seamlessly across all client implementations.

for model in "gemini-2.5-pro" "gemini-2.5-flash" "gemini-3-flash-preview" "gemini-3.1-pro-preview" "gpt-4.1" "gpt-4.1-mini" "gpt-4.1-nano" "claude-opus-4-6" "claude-sonnet-4-6"; do
  echo "=================================================="
  echo "🧪 Testing Model: $model"
  echo "=================================================="

  curl -s -X POST http://localhost:9888/api/v1/chatbot/chat \
    -H "Content-Type: application/json" \
    -d '{
      "query": "Give me all the information there is about the current state of the cluster",      
      "model": "'"$model"'"
    }' | jq

  echo -e "\n"
done

Attached are the test results after evaluating each provider model by asking a question and recording its response - testingChatBot.txt

3. Test Results

Routing Validation: The LLMDispatcher successfully identified the intended provider based solely on the requested model name string (e.g., routing gpt-4.1 to the OpenAIClient, and gemini-2.5-flash to the GeminiClient).
Tool Execution Validation: All tested models successfully reasoned over the updated recon-api-guide.md, selected the correct Recon backend API endpoint (/clusterState), executed the API call internally, and summarized the JSON payload back into natural English.
Error Handling Validation: The dispatcher correctly identified and gracefully handled missing configuration errors when attempting to route to Anthropic models (claude-opus-4-6, claude-sonnet-4-6) without an API key present, returning expected JSON errors: {"error": "No API key configured for provider 'anthropic'."}

…ini integration.

devmadhuu

@ArafatKhan2198 thanks for the patch, few comments at a high level in initial review. Please check.

Also one observation as per output you mentioned in PR description, various models output for same question: "Give me all the information there is about the current state of the cluster", I can see some wrong answers even. E.g. for gemini-3-flash-preview, it says that "All 12 internal Recon tasks are functioning correctly". Not sure from where the model got 12 tasks. This is surely it is hallucinating.

priyeshkaratha

Thanks @ArafatKhan2198 for the patch. Please check the comments.

github-actions · 2026-04-18T00:13:16Z

This PR has been marked as stale due to 21 days of inactivity. Please comment or remove the stale label to keep it open. Otherwise, it will be automatically closed in 7 days.

priyeshkaratha

Thanks @ArafatKhan2198 for updating the patch. Please check the inline comment. Apart from the code overall LGTM

devmadhuu

@ArafatKhan2198 , thanks for the patch. Still some issues are not fixed. Kindly check. And current PR design needs to make flexible and extensible for future MCP perspective as current PR code is not extensible, but can be doable in next PR, but to merge this PR, needs to handle bare minimum comments.

And we can think working direction to make it more extensible, following points are major, but lets not handle in current PR.

Step 1: Extract Agent interface from ChatbotAgent. ChatbotAgent becomes ReconApiAgent implements Agent. The Guice module binds Set via Multibindings. ChatbotEndpoint talks to a new AgentOrchestrator (or just the Agent directly for now with a trivial single-agent router).

Step 2: Extract DataSourceExecutor interface from ToolExecutor. ToolExecutor becomes ReconRestExecutor implements DataSourceExecutor. Each Agent gets injected with the appropriate executor(s). A future JmxMetricsAgent would be injected with JmxHttpExecutor which simply wraps the existing JmxServiceProviderImpl.

Step 3: Make apiSchema a per-agent concern, not a singleton field. Each Agent loads its own tool schema. The AgentOrchestrator's tool-selection prompt is composed dynamically from all registered agents' schemas — a simple String.join across agent.getSchema().

devmadhuu · 2026-05-11T11:37:03Z

+    String fullEndpoint = endpoint;
+
+    // Ensure the path always starts with "/api/v1/"
+    if (!fullEndpoint.startsWith("/api/v1/")) {


@ArafatKhan2198 this is still not resolved. Basically ToolExecutor.normalizeEndpoint() only ensures the path starts with /api/v1/, but a compromised prompt or a hallucinating LLM could inject paths like /api/v1/../actuator/shutdown or /api/v1/%2F..%2F. You should maintain an allowlist of accepted path prefixes (e.g., /api/v1/containers, /api/v1/datanodes, etc.) and reject anything not on the list. The current requireSafeScope guard only checks for listKeys — it provides no protection for other endpoints.

devmadhuu

One critical and few nits.

adoroszlai

Please do take a look at CI results in fork.

adoroszlai · 2026-05-28T17:13:29Z

+      <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-anthropic</artifactId>
+        <version>0.36.2</version>
+      </dependency>
+      <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-core</artifactId>
+        <version>0.36.2</version>
+      </dependency>
+      <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-google-ai-gemini</artifactId>
+        <version>0.36.2</version>
+      </dependency>
+      <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-open-ai</artifactId>
+        <version>0.36.2</version>
+      </dependency>


every other third-party library in the project follows this same pattern of individual version entries. Introducing a BOM import for just this one library would be inconsistent with how the rest of the project is structured.

BOM import has been in use for quite some time now, so please do switch to langchain4j-bom:

ozone/pom.xml

Lines 229 to 327 in cfb8ade

<dependency>

<groupId>com.fasterxml.jackson</groupId>

<artifactId>jackson-bom</artifactId>

<version>${jackson2-bom.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>com.google.inject</groupId>

<artifactId>guice-bom</artifactId>

<version>${guice.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>io.grpc</groupId>

<artifactId>grpc-bom</artifactId>

<version>${io.grpc.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>io.netty</groupId>

<artifactId>netty-bom</artifactId>

<version>${netty.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>io.opentelemetry</groupId>

<artifactId>opentelemetry-bom</artifactId>

<version>${opentelemetry.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.apache.iceberg</groupId>

<artifactId>iceberg-bom</artifactId>

<version>${iceberg.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.eclipse.jetty</groupId>

<artifactId>jetty-bom</artifactId>

<version>${jetty.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.glassfish.jersey</groupId>

<artifactId>jersey-bom</artifactId>

<version>${jersey2.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.jetbrains.kotlin</groupId>

<artifactId>kotlin-bom</artifactId>

<version>${kotlin.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.junit</groupId>

<artifactId>junit-bom</artifactId>

<version>${junit5.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.mockito</groupId>

<artifactId>mockito-bom</artifactId>

<version>${mockito.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>



<groupId>org.ow2.asm</groupId>

<artifactId>asm-bom</artifactId>

<version>${asm.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.slf4j</groupId>

<artifactId>slf4j-bom</artifactId>

<version>${slf4j.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

<dependency>

<groupId>org.springframework</groupId>

<artifactId>spring-framework-bom</artifactId>

<version>${spring.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

Even if BOM is not available for some dependency, please define a property for consistent versioning of multi-module dependency, example:

ozone/pom.xml

Lines 517 to 526 in cfb8ade

<dependency>

<groupId>info.picocli</groupId>

<artifactId>picocli</artifactId>

<version>${picocli.version}</version>

</dependency>

<dependency>

<groupId>info.picocli</groupId>

<artifactId>picocli-shell-jline3</artifactId>

<version>${picocli.version}</version>

</dependency>

adoroszlai · 2026-05-28T17:15:43Z

+    <dependency>
+      <groupId>dev.langchain4j</groupId>
+      <artifactId>langchain4j-core</artifactId>
+    </dependency>


Jar files under share/ozone/lib in the build have changed. Please update: * hadoop-ozone/dist/src/main/license/bin/LICENSE.txt (add new dependencies with the appropriate license, delete any removed dependencies) * hadoop-ozone/dist/src/main/license/jar-report.txt (based on the diff shown below) If you notice unexpected differences (can happen when the check is run in a fork), please first update your branch from upstream master to get any other recent dependency changes. If you are running this locally after build with -DskipShade, please ignore any ozone-filesystem jars reported to be missing. Changes detected: --- /dev/fd/63 2026-05-27 10:02:54.566056827 +0000 +++ /dev/fd/62 2026-05-27 10:02:54.566056827 +0000 @@ -35,6 +35,7 @@ share/ozone/lib/commons-pool2.jar share/ozone/lib/commons-text.jar share/ozone/lib/commons-validator.jar +share/ozone/lib/converter-jackson.jar share/ozone/lib/curator-client.jar share/ozone/lib/curator-framework.jar share/ozone/lib/derby.jar @@ -158,6 +159,7 @@ share/ozone/lib/jsp-api.jar share/ozone/lib/jspecify.jar share/ozone/lib/jsr311-api.jar +share/ozone/lib/jtokkit.jar share/ozone/lib/kerb-core.jar share/ozone/lib/kerb-crypto.jar share/ozone/lib/kerb-util.jar @@ -165,7 +167,14 @@ share/ozone/lib/kerby-config.jar share/ozone/lib/kerby-pkix.jar share/ozone/lib/kerby-util.jar +share/ozone/lib/kotlin-stdlib-common.jar +share/ozone/lib/kotlin-stdlib-jdk7.jar +share/ozone/lib/kotlin-stdlib-jdk8.jar share/ozone/lib/kotlin-stdlib.jar +share/ozone/lib/langchain4j-anthropic.jar +share/ozone/lib/langchain4j-core.jar +share/ozone/lib/langchain4j-google-ai-gemini.jar +share/ozone/lib/langchain4j-open-ai.jar share/ozone/lib/listenablefuture-empty-to-avoid-conflict-with-guava.jar share/ozone/lib/log4j-api.jar share/ozone/lib/log4j-core.jar @@ -193,7 +202,11 @@ share/ozone/lib/netty-transport.Final.jar share/ozone/lib/nimbus-jose-jwt.jar share/ozone/lib/okhttp-jvm.jar +share/ozone/lib/okhttp-sse.jar +share/ozone/lib/okhttp.jar share/ozone/lib/okio-jvm.jar +share/ozone/lib/okio.jar +share/ozone/lib/openai4j.jar share/ozone/lib/opentelemetry-api.jar share/ozone/lib/opentelemetry-common.jar share/ozone/lib/opentelemetry-context.jar @@ -259,6 +272,7 @@ share/ozone/lib/re2j.jar share/ozone/lib/reflections.jar share/ozone/lib/reload4j.jar +share/ozone/lib/retrofit.jar share/ozone/lib/rocksdb-checkpoint-differ.jar share/ozone/lib/rocksdbjni.jar share/ozone/lib/simpleclient.jar

https://github.com/ArafatKhan2198/ozone/actions/runs/26503992485/job/78053259617#step:13:18

Done. I've updated both jar-report.txt and LICENSE.txt to include the new transitive dependencies introduced by LangChain4j (such as jtokkit, okhttp, retrofit, and kotlin-stdlib).

adoroszlai · 2026-05-28T17:17:17Z

+        <artifactId>langchain4j-core</artifactId>
+        <version>0.36.2</version>


This does not work with Java 8.

Error: bad class file: /home/runner/.m2/repository/dev/langchain4j/langchain4j-core/0.36.2/langchain4j-core-0.36.2.jar(dev/langchain4j/data/message/AiMessage.class) Error: class file has wrong version 61.0, should be 52.0

Thanks for pointing this out. LangChain4j officially dropped Java 8 support starting with 0.36.0.

I have downgraded the langchain4j.version to 0.35.0. This is the latest release that should compiles to Java 8.

adoroszlai · 2026-05-28T17:18:19Z

Files with unapproved licenses: /home/runner/work/ozone/ozone/hadoop-ozone/recon/src/main/resources/chatbot/recon-summarization-prompt.txt /home/runner/work/ozone/ozone/hadoop-ozone/recon/src/main/resources/chatbot/recon-fallback-prompt-template.txt /home/runner/work/ozone/ozone/hadoop-ozone/recon/src/main/resources/chatbot/recon-api-guide.md /home/runner/work/ozone/ozone/hadoop-ozone/recon/src/main/resources/chatbot/recon-tool-selection-prompt-preamble.txt

I tried to avoid adding license headers to these files, as the raw text is fed directly to the LLM and the header might interfere with the prompts. Instead, I have added it to rat-exclusions.txt to exclude the chatbot resources directory from the RAT check.

…on chatbot.

devmadhuu

Thanks @ArafatKhan2198 , LGTM +1. Just a nit for adding log. PR approved. Add the log.

devmadhuu

Please check few minor comments.

devmadhuu · 2026-06-01T10:39:40Z

+
+  // ── Execution policy ────────────────────────────────────────
+  public static final String OZONE_RECON_CHATBOT_EXEC_MAX_RECORDS = OZONE_RECON_CHATBOT_PREFIX
+      + "exec.max.records";


If this is really needed.

devmadhuu · 2026-06-01T10:40:21Z

+        ChatbotConfigKeys.OZONE_RECON_CHATBOT_EXEC_PAGE_SIZE,
+        ChatbotConfigKeys.OZONE_RECON_CHATBOT_EXEC_PAGE_SIZE_DEFAULT);
+
+    LOG.info("ToolExecutor initialized with Recon URL: {}, connectTimeoutMs={}, " +


Pls check if configs are needed in this class to read.

ArafatKhan2198 · 2026-06-02T06:58:13Z

Green Run - https://github.com/ArafatKhan2198/ozone/actions/runs/26800762880

adoroszlai

@ArafatKhan2198 There are still some minor problems with the patch already merged (note that I only checked the dependency sections, not the actual implementation). BTW, next time please mention that AI assistance was used for implementing the changes (see policy).

adoroszlai · 2026-06-02T11:55:31Z

 OZONE-SITE.XML_ozone.om.http-address=om:9874
 OZONE-SITE.XML_ozone.scm.http-address=scm:9876
-OZONE-SITE.XML_ozone.scm.container.size=100MB
+OZONE-SITE.XML_ozone.scm.container.size=1GB


Why was this changed? We use a small value to reduce chances of disk out of space error in acceptance tests.

adoroszlai · 2026-06-02T11:57:54Z

+Apache License 2.0
+=====================
+   com.squareup.okhttp3:okhttp
+   com.squareup.okhttp3:okhttp-sse
+   com.squareup.okio:okio
+   com.squareup.retrofit2:converter-jackson
+   com.squareup.retrofit2:retrofit
+   dev.ai4j:openai4j
+   dev.langchain4j:langchain4j-anthropic
+   dev.langchain4j:langchain4j-core
+   dev.langchain4j:langchain4j-open-ai
+   org.jetbrains.kotlin:kotlin-stdlib-common
+   org.jetbrains.kotlin:kotlin-stdlib-jdk7
+   org.jetbrains.kotlin:kotlin-stdlib-jdk8
+
 Apache License 2.0
 =====================


Please don't duplicate License sections, add the dependencies in existing sections in alphabetical order.

Created HDDS-15469 for this.

adoroszlai · 2026-06-02T11:58:18Z

-share/ozone/lib/apache-log4j-extras.jar
-share/ozone/lib/aopalliance.jar
 share/ozone/lib/aopalliance-repackaged.jar
+share/ozone/lib/aopalliance.jar
+share/ozone/lib/apache-log4j-extras.jar


Please don't move around lines unnecessarily.

adoroszlai · 2026-06-02T12:03:26Z

+      <dependency>
+        <!-- langchain4j-bom pins JUnit 5.10.0; override to keep Ozone on ${junit5.version}. -->
+        <groupId>org.junit.jupiter</groupId>
+        <artifactId>junit-jupiter-api</artifactId>
+        <version>${junit5.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>org.junit.jupiter</groupId>
+        <artifactId>junit-jupiter-params</artifactId>
+        <version>${junit5.version}</version>
+      </dependency>


We already import junit-bom.

ozone/pom.xml

Lines 300 to 306 in 2020d86

<dependency>

<groupId>org.junit</groupId>

<artifactId>junit-bom</artifactId>

<version>${junit5.version}</version>

<type>pom</type>

<scope>import</scope>

</dependency>

This will be fixed in #10421.

adoroszlai · 2026-06-02T12:09:07Z

+      <dependency>
+        <!-- langchain4j-bom pins AWS SDK 2.21.44; override to keep Ozone on ${aws-java-sdk2.version}. -->
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>apache-client</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>auth</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>aws-core</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>http-client-spi</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>identity-spi</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>regions</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>s3</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>s3-transfer-manager</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>sdk-core</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>software.amazon.awssdk</groupId>
+        <artifactId>utils</artifactId>
+        <version>${aws-java-sdk2.version}</version>
+      </dependency>


These are unnecessary. AWS SDK v2 is only used in tests and that module uses the BOM:

ozone/hadoop-ozone/integration-test-s3/pom.xml

Lines 29 to 30 in 2020d86



<aws-java-sdk2.version>2.44.12</aws-java-sdk2.version>

This will also be fixed in #10421.

devmadhuu · 2026-06-03T16:38:21Z

@ArafatKhan2198 though PR is merged by you, but as discussed, I still don't see any test if chatbot is functional in secure cluster which is bare minimum requirement.

ArafatKhan2198 changed the title ~~Integrate an AI Assistant to Recon.~~ HDDS-14816. Add Recon AI Assistant backend foundation with Google Gemini integration Mar 13, 2026

HDDS-14816. Add Recon AI Assistant backend foundation with Google Gem…

287c739

…ini integration.

ArafatKhan2198 force-pushed the HDDS-14816 branch from fc5c38b to 287c739 Compare March 13, 2026 08:42

ArafatKhan2198 added 5 commits March 13, 2026 22:06

Fixed Compilation Issues

8871b81

Made Improvements to prompt and code

03c34ff

Refactored code

fbe9140

Improved the comments and refactored the code a bit

66253a4

Simplify LLM Provider architecture using Composition

908bfb5

devmadhuu self-requested a review March 17, 2026 07:12

devmadhuu reviewed Mar 18, 2026

View reviewed changes

priyeshkaratha reviewed Mar 27, 2026

View reviewed changes

github-actions Bot added the stale label Apr 18, 2026

ArafatKhan2198 changed the title ~~HDDS-14816. Add Recon AI Assistant backend foundation with Google Gemini integration~~ HDDS-14816. Add Recon AI Assistant backend foundation with Multi LLM integration Apr 22, 2026

github-actions Bot removed the stale label Apr 23, 2026

ArafatKhan2198 marked this pull request as ready for review April 24, 2026 08:38

ArafatKhan2198 marked this pull request as draft April 24, 2026 08:38

ArafatKhan2198 requested review from devmadhuu and priyeshkaratha May 5, 2026 08:20

priyeshkaratha reviewed May 8, 2026

View reviewed changes

Comment thread hadoop-ozone/recon/src/main/java/org/apache/hadoop/ozone/recon/chatbot/security/LLMClient2.java Outdated

ArafatKhan2198 added 3 commits May 11, 2026 14:30

Fixed review comment changes

f3d4185

Added a single provider for LLM request creation and response parsing

45369ee

Made the avaliable models configurable

2a74402

devmadhuu reviewed May 11, 2026

View reviewed changes

ArafatKhan2198 added 4 commits May 12, 2026 00:08

Added security checks for allowed endpoint prefixes

37ed873

Moved the prompt to separate files

8abd92b

Improve the tool selection prompt

bc3142d

Made structural changes

fc45b8b

ArafatKhan2198 force-pushed the HDDS-14816 branch from fabbd8b to fc45b8b Compare May 11, 2026 19:49

Final review comments

7f3407c

devmadhuu self-requested a review May 20, 2026 12:19

devmadhuu reviewed May 20, 2026

View reviewed changes

ArafatKhan2198 added 4 commits May 24, 2026 00:39

Made changes

ab86e75

Added tests for validation

d65ff1e

Fixed final review comments

ec3d1d8

Added more tests

deb80c3

adoroszlai requested changes May 28, 2026

View reviewed changes

ArafatKhan2198 added 9 commits May 29, 2026 13:57

Added tests for list keys

f8a513b

Created a separate Utils class for the chatbot

4405d0d

Use langchain4j-bom 0.35.0 and fix dependency/license fallout for Rec…

0cdb4e8

…on chatbot.

Fixed the missing Jars mentions in the report

763b068

Refactor(recon): Fix PMD static analysis violations in chatbot modules.

854c21b

Fixed Findbugs Issues

5f65bf3

Fixed checkstyle Issues

ecf4664

Improved the context doc

23b3652

Removed commented code used for testing

fab5431

devmadhuu approved these changes Jun 1, 2026

View reviewed changes

Comment thread ...one/recon/src/main/java/org/apache/hadoop/ozone/recon/chatbot/llm/LangChain4jDispatcher.java

Final changes commited for the bugs found in testing

073f79c

devmadhuu reviewed Jun 1, 2026

View reviewed changes

ArafatKhan2198 added 5 commits June 1, 2026 23:41

Fixed Admin filter test failing

7db5606

Removed the redundant config and improved the log messaging

cfd3a77

Fixed depdency Issue

6540262

Merge branch 'master' into HDDS-14816

2245ed7

Fixed checkstyle

7430c00

priyeshkaratha approved these changes Jun 2, 2026

View reviewed changes

ArafatKhan2198 marked this pull request as ready for review June 2, 2026 06:46

ArafatKhan2198 merged commit 2020d86 into apache:master Jun 2, 2026
61 checks passed

adoroszlai reviewed Jun 2, 2026

View reviewed changes

	<dependency>
	<groupId>com.fasterxml.jackson</groupId>
	<artifactId>jackson-bom</artifactId>
	<version>${jackson2-bom.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>com.google.inject</groupId>
	<artifactId>guice-bom</artifactId>
	<version>${guice.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>io.grpc</groupId>
	<artifactId>grpc-bom</artifactId>
	<version>${io.grpc.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>io.netty</groupId>
	<artifactId>netty-bom</artifactId>
	<version>${netty.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>io.opentelemetry</groupId>
	<artifactId>opentelemetry-bom</artifactId>
	<version>${opentelemetry.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.apache.iceberg</groupId>
	<artifactId>iceberg-bom</artifactId>
	<version>${iceberg.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.eclipse.jetty</groupId>
	<artifactId>jetty-bom</artifactId>
	<version>${jetty.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.glassfish.jersey</groupId>
	<artifactId>jersey-bom</artifactId>
	<version>${jersey2.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.jetbrains.kotlin</groupId>
	<artifactId>kotlin-bom</artifactId>
	<version>${kotlin.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.junit</groupId>
	<artifactId>junit-bom</artifactId>
	<version>${junit5.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.mockito</groupId>
	<artifactId>mockito-bom</artifactId>
	<version>${mockito.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<!-- Transitive dependency via various direct dependencies. Import BOM to ensure consistent versions. -->
	<groupId>org.ow2.asm</groupId>
	<artifactId>asm-bom</artifactId>
	<version>${asm.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.slf4j</groupId>
	<artifactId>slf4j-bom</artifactId>
	<version>${slf4j.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>
	<dependency>
	<groupId>org.springframework</groupId>
	<artifactId>spring-framework-bom</artifactId>
	<version>${spring.version}</version>
	<type>pom</type>
	<scope>import</scope>
	</dependency>

	<dependency>
	<groupId>info.picocli</groupId>
	<artifactId>picocli</artifactId>
	<version>${picocli.version}</version>
	</dependency>
	<dependency>
	<groupId>info.picocli</groupId>
	<artifactId>picocli-shell-jline3</artifactId>
	<version>${picocli.version}</version>
	</dependency>

		<artifactId>langchain4j-core</artifactId>
		<version>0.36.2</version>

	<!-- move to root POM when needed in any other module -->
	<aws-java-sdk2.version>2.44.12</aws-java-sdk2.version>

Uh oh!

Conversation

ArafatKhan2198 commented Mar 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What changes were proposed in this pull request?

What the Recon AI Chatbot Does (For Context)

Recon AI Chatbot: Backend Architecture Guide - https://docs.google.com/document/d/1jyYZz0llKwN7lexJzVRjxfzl1Iwdbx8dABwLXGzAajQ/edit?tab=t.0

What is the link to the Apache JIRA

How was this patch tested?

How was this patch tested?

1. Configuration Setup

2. API Verification Script

Attached are the test results after evaluating each provider model by asking a question and recording its response - testingChatBot.txt

3. Test Results

Uh oh!

devmadhuu left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

priyeshkaratha left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

github-actions Bot commented Apr 18, 2026

Uh oh!

priyeshkaratha left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

devmadhuu left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

devmadhuu left a comment

Choose a reason for hiding this comment

Uh oh!

adoroszlai left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devmadhuu left a comment

Choose a reason for hiding this comment

Uh oh!

ArafatKhan2198 commented Mar 13, 2026 •

edited

Loading